# Rethinking Zero-Shot Time Series Classification: From Task-specific Classifiers to In-Context Inference

arXiv: https://arxiv.org/abs/2602.00620 · HTML: https://mlsanity.com/paper/2602.00620/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 31 Jan 2026.

## Builds on (most cited first, 28 of 28)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [Are Transformers universal approximators of sequence-to-sequence functions?](https://mlsanity.com/paper/1912.10077/) (2019)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [Foundation Models for Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2403.14735/) (2024)
- [Chronos-2: From Univariate to Universal Forecasting](https://mlsanity.com/paper/2510.15821/) (2025)
- [One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention](https://mlsanity.com/paper/2307.03576/) (2023)
- [Looped Transformers are Better at Learning Learning Algorithms](https://mlsanity.com/paper/2311.12424/) (2023)
- [The Learnability of In-Context Learning](https://mlsanity.com/paper/2303.07895/) (2023)
- [TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning](https://mlsanity.com/paper/2505.23719/) (2025)
- [Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?](https://mlsanity.com/paper/2410.08292/) (2024)
- [Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective](https://mlsanity.com/paper/2406.00793/) (2024)
- [In-Context Fine-Tuning for Time-Series Foundation Models](https://mlsanity.com/paper/2410.24087/) (2024)
- [In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization](https://mlsanity.com/paper/2402.14951/) (2024)
- [Universal approximations of permutation invariant/equivariant functions by deep neural networks](https://mlsanity.com/paper/1903.01939/) (2019)
- [In-context Time Series Predictor](https://mlsanity.com/paper/2405.14982/) (2024)
- [NuTime: Numerically Multi-Scaled Embedding for Large-Scale Time-Series Pretraining](https://mlsanity.com/paper/2310.07402/) (2023)
- [Data Augmentation for Time-Series Classification: An Extensive Empirical Study and Comprehensive Survey](https://mlsanity.com/paper/2310.10060/) (2023)
- [Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification](https://mlsanity.com/paper/2510.26777/) (2025)
- [The Initialization Determines Whether In-Context Learning Is Gradient Descent](https://mlsanity.com/paper/2512.04268/) (2025)

## Built on by (most cited first, 3 of 3)

- [Forecasting Is Not Attribution: Localizing Decoder Bypass in Graph-Based Neural Marketing Mix Models](https://mlsanity.com/paper/2606.12687/) (2026)
- [TimEE: End-to-end Time Series Classification via In-Context Learning](https://mlsanity.com/paper/2607.07500/) (2026)
- [ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning](https://mlsanity.com/paper/2608.24033/) (2026)

## Abstract (arXiv)

The zero-shot evaluation of time series foundation models (TSFMs) for classification typically uses a frozen encoder followed by a task-specific classifier. However, this practice violates the training-free premise of zero-shot deployment and introduces evaluation bias due to classifier-dependent training choices. To address this issue, we propose TIC-FM, an in-context learning framework that treats the labeled training set as context and predicts labels for all test instances in a single forward pass, without parameter updates. TIC-FM pairs a time series encoder and a lightweight projection adapter with a split-masked latent memory Transformer. We further provide theoretical justification that in-context inference can subsume trained classifiers and can emulate gradient-based classifier training within a single forward pass. Experiments on 128 UCR datasets show strong accuracy, with consistent gains in the extreme low-label situation, highlighting training-free transfer for time series classification.The source code is publicly available at https://github.com/fangjuntao/TIC-FM.